人工智能代理 Jobs

We are a Mortgage Broking company in Australia seeking a full‑time Marketing & Automation Specialist with advanced GoHighLevel expertise. You will manage end‑to‑end lead generation across Social Media, Google Ads, LinkedIn, and build fully automated workflows for Home Loans, Refinances, SMSF Loans, Car Loans, and Business Loans. Must be highly skilled in GHL automation, AI agents, appointment booking, nurturing sequences, and multi‑channel campaign management. KPIs include lead volume, CPL, appointment rate, workflow uptime, and reporting accuracy. Here’s what I’m after: To build, manage, and optimise end‑to‑end lead generation systems across Social Media, Google Ads, LinkedIn, and GoHighLevel — delivering consistent qualified appointments for Home Loans, Refinances,...

I have an existing set up of amazon’s bedrock agent core gateway which host agents and tools like k6, speedcurve , loadrunner , dynatrace , jira , teams . Agent is invoked on evey code push to github . I need similar set up in azure cloud . Build an analysis agents built with Azure AI Foundry. GitHub Push ↓ Azure AI Foundry (agent orchestration) ↓ API Management (gateway) ↓ Azure Functions / APIs / Tools ↓ LoadRunner / Dynatrace / Lighthouse / Teams / Jira attaching the existing set up diagram using aws bedrock agentcore

I need a small, reliable agent that is hosted on agent core runtime and can be involved after every test run for Root cause analysis . The agent connects to the AWS account and routinely pulls CloudWatch data from a ECS cluster that host 15 microservices . The focus is on five metrics—CPU utilization, Memory usage, Request count, Response time, and Error rate—so the solution must fetch both the default statistics and the custom ones that require the CloudWatch Agent or an equivalent approach. AWS is our only cloud provider, and ECS cluster is the only service in scope, so the code can stay lightweight. I am comfortable running the agent as either a Python script (boto3), a serverless Lambda, Deliverables • Source code with clear comments . walkthrough of the code...

I need a full-fledged conversational agent built on 11 Labs that can handle end-to-end sales assistance while sounding natural and genuinely helpful. The bot must be able to greet prospects, qualify their needs, recommend products or services, and nudge them toward purchase—all with individually tailored replies rather than canned FAQ answers. Channel coverage is key: visitors should meet the agent in our website chat widget, receive follow-up emails when needed, and even get timely SMS nudges or order confirmations. Whichever medium a customer chooses, the context of the conversation must travel with them so the dialogue feels continuous. Here is what I expect when we wrap up: • A trained 11 Labs model (or pipeline that calls 11 Labs) fine-tuned for my brand’s ton...

I am a developer by background, and I am currently working on building a custom AI agent. The agent is intended to read subscribers' chat histories and answer questions based on past conversations. While I have experience as a data analyst and data scraper, I am not an LLM engineer. I need a general guide and a simple script that would allow me to conduct initial testing. Given this project is still in its early stages and I am operating on a limited budget. Once documentation and python script are working, this project will be closed. Documentation is mandatory and ai bid will be ignored. Only individual freelancers! Thank you.

We are looking for an experienced full-stack developer with a strong background in B2B SaaS application development to join a long-term project. The ideal candidate should have hands-on experience with , Supabase, multi-AI-agent systems, security best practices, scalable architecture, and clean, well-documented code. This project involves building a professional B2B SaaS platform with AI-driven workflows, secure user authentication, database management, role-based access, API integrations, and a clean, production-ready user experience. We need someone who can understand business requirements, propose the best technical approach, execute efficiently, test thoroughly, and support deployment. Our workflow: First, you will submit a clear technical proposal and implementation plan. We will rev...

We are looking for an Agentic AI Specialist to help build and deliver multi-agent AI systems for small business clients. We work on voice ordering bots, email automation pipelines, scheduling agents, and estimate generators — real production builds, not demos. Responsibilities: • Design and build multi-agent systems using Claude Code, LangGraph, AutoGen, or CrewAI • Integrate agents with APIs including CRMs, POS systems, calendars, and email platforms • Configure MCP servers to connect agents to live data and services • Write clean Python with proper error handling, retry logic, and fallback behavior • Debug agent loops, hallucination issues, and tool-use failures in production Requirements: • Hands-on experience building agentic AI pipelines (GitH...

I’m planning a series of projects that revolve around injecting advanced AI into new and existing products, and I’m looking for one reliable development partner to grow with me over the long haul. Every build will lean heavily on Large Language Models, purpose-built AI agents and traditional machine-learning models, so you’ll need to feel at home with frameworks such as LangChain or similar, prompt-engineering best practices, fine-tuning workflows and containerised model deployment. The roadmap includes: • Green-field SaaS platforms with secure, multi-tenant user authentication, rich report generation and deep third-party API integrations. • Companion desktop utilities (likely Electron or a comparable cross-platform stack) that tap into the same AI core. ...

I need an AI-driven chatbot that lives inside WhatsApp and answers everyday questions about our products and services. Its purpose is strictly general inquiries, so the experience must feel like texting a friendly teammate—concise, helpful, and casual. The bot should understand open-ended queries, remember short-term context, and share quick links, images, or short text snippets when that speeds things up. Whenever a request goes beyond its knowledge, it must hand the chat off to a human agent inside the same WhatsApp thread. I’m open to Dialogflow, Rasa, or a clean custom build on the WhatsApp Business API, provided the setup stays simple enough for my in-house dev to maintain. Deliverables • A fully functional WhatsApp chatbot hosted on a cloud platform (AWS, GCP, or ...

Hello, We are launching a new technology project focused on the fitness industry. Our company already works with gyms through equipment supply and maintenance services, and now we are planning to build a white-label CRM and automation platform for gym businesses using GoHighLevel. We are looking for an experienced GoHighLevel expert or development team for full project development and long-term collaboration. Project requirements include: • White-label GoHighLevel SaaS setup • Multi-client / multi-gym account structure • CRM workflows and automation systems • WhatsApp API integration and centralized communication • Lead management and sales pipelines • Membership reminders and automated follow-ups • Integration with gym management systems or data imp...

Our in-house ERP is built on Laravel, and I need a WhatsApp automation layer that can: • Engage customers instantly for support, order processing, and any quick information they need. • Walk them through a dynamic, decision-based flow that adapts to each client’s requirements instead of forcing a rigid “push-to-agent” model. • Handle the routine work—answering FAQs, sending pre-built packages or PDFs, sharing account/order status—then pass the conversation to a live agent only when a brand-new or complex request appears. I already have WhatsApp Business API access; what I need from you is the full conversational logic, webhook callbacks, and a clean Laravel module (controllers, services, migrations if required) that drops straight into our...

Project Overview I am a business owner with four safety gear brands (manufacturing). I want to migrate data from our company server into a private, local knowledge base on my laptop and set up an AI agent (Claw/OpenClaw-style) to work with that data for complex business tasks. Scope of Work / Deliverables Data Indexing & Knowledge Base (RAG) Set up a local "brain" (Vector DB like AnythingLLM, ChromaDB, or LlamaIndex). Create a workflow to ingest/sync folders of business data (Product Specs, OSHA manuals, Pricing, Order History). Ensure the agent can "retrieve" relevant facts from these files before answering. Agent Framework (Claw / OpenClaw) Install and configure the agentic framework on my machine. Connect it to the Knowledge Base as a "tool." Connect t...

I need an AI agent that runs entirely on my VPS, loads through Ollama, and uses the Qwen‑3 14B or 32B model. There must be zero external API calls for inference everything stays local. The agent must listen to my Office 365 mailbox via a Microsoft Graph Webhook and process every new message within a maximum delay of five minutes. Workflow requirements When an email arrives, the agent should: • parse intent, entities, urgency, required actions, sentiment, and deadlines • decide whether to:  (a) create a follow‑up task in Corteza CRM  (b) schedule a meeting  (c) draft a context‑aware reply • push the chosen action back to the relevant system through its API (Corteza or Microsoft Graph) The agent must be idempotent and avoid double‑processing emails (store pr...

I have an in-house AI agent that triggers k6 load test based on github push or github webhook events , but it still misses two critical situations: Identifying code updates and new feature additions and update the scripts or create new scripts accordingly , I need that gap closed. I have around 2000 selenium and playwright scripts and 100+ loadrunner and k6 scripts , the agent should work on all those existing scripts For development purposes i will share a test application repo , we can use this repo to evaluate the agent The project is partially developed, it creates selenium, k6 and loadrunner scripts and deployed in aws bedrock agent core runtime . we need to add playwright and make the overall solution more robust to support complex flows like journey flows in the script . You...

We are looking to build an Agent AI which : Takes the input of quotation request from Email, PDF, Images, Website Enquiry Extract the data of enquiry and check the erp system to match the right products for the requirement Prepare a quotation based on the customer requirement and available products Checks wheather the quotation is right or not Sends to sales team for approval and once approved sends to end customer ERP is already there and built with PHP. API's should be created from ERP to communicate with Agent. Agent should be able to understand products and map them with customer requirements through cementic approach. Agent should not invent. We need to know the cost and timeline if : Agent is built from scratch using LLM, LangGraph, Python etc and if created using already...

We are looking to build an Agent AI which : Takes the input of quotation request from Email, PDF, Images, Website Enquiry Extract the data of enquiry and check the erp system to match the right products for the requirement Prepare a quotation based on the customer requirement and available products Checks wheather the quotation is right or not Sends to sales team for approval and once approved sends to end customer ERP is already there and built with PHP. API's should be created from ERP to communicate with Agent. Agent should be able to understand products and map them with customer requirements through cementic approach. Agent should not invent. We need to know the cost and timeline if : Agent is built from scratch using LLM, LangGraph, Python etc and if created using already...

Agentic AI Engineer — Optimize Our Media Monitoring Stack (Policy / Public Affairs) About the Role We run a media monitoring operation in the public policy space and need an experienced agentic AI engineer to help us **optimize an existing stack** — not build from scratch. We already have a working system; we want to push its quality, precision, and coverage substantially higher. You’ll be working with someone who knows this space and has strong opinions about agent architecture, retrieval strategies, and prompt design. We’re looking for a peer who can pressure-test our setup and make it noticeably better. What We’re Monitoring - **Approximately 600-800 keywords** — policy terms, organizations, named entities, legislation, and topical phrases - **Ap...

Project OverviewI am seeking an expert to build a fully autonomous operational engine for an event services marketplace (B2B, B2C, and C2B). My platform connects users with professionals and vendors for multi-task event services. I need a Hermes Agent implementation that doesn't just post content, but acts as a backend manager handling tickets, payments, and deep user history across my website and social Tech StackAgent Framework: Hermes AgentSocial Orchestration: Postiz (Open Source)Integrations: Composio / Python / [Your CMS] API / Payment Gateways (e.g., Stripe)Control Interface: Telegram or Discord (Human-in-the-Loop)Database: Pinecone/SQLite (for Transactional & User History)Key DeliverablesDeployment: Full installation of Hermes on a dedicated server (VPS) with secure Auto...

I have an in-house AI agent that triggers k6 load test based on github push or github webhook events , but it still misses two critical situations: Identifying code updates and new feature additions and update the scripts or create new scripts , I need that gap closed. Your task is to create a new agent so it watches a codebase , create k6 , loadrunner, selenium scripts for new functionality or update exiting scripts to add new functionality .let the implementation be Python only Once a change is spotted the agent must automatically adjust our existing automation and performance test scripts, regenerating or patching them so CI runs green without manual edits. The current pipeline is circleci -based with k6 and loadrunner for performance checks; hooks are already in place, they just nee...

Budowa Agenta AI do automatyzacji Marketplace (400 SKU na początek) Cel projektu: Stworzenie autonomicznego agenta AI, który będzie zarządzał asortymentem (400 produktów) na platformach Allegro i Amazon. System ma pilnować jakości ofert, monitorować konkurencję i automatyzować proces listowania. Kluczowe moduły do wdrożenia:
Monitoringu & Dynamic Pricing: Agent ma sprawdzać ceny konkurencji przez API i sugerować zmiany (lub wprowadzać je w oparciu o ustalone reguły marżowe).
Quality Assurance (AI Editor): Automatyczna optymalizacja opisów, tytułów i parametrów pod SEO/A+ Content przy użyciu LLM (np. GPT-4o lub Gemini Pro).
Inventory Sync: Integracja z bazą danych (np. Google Sheets / Airtable) i synchronizacja stanów przez API (BaseLinker lub b...

The goal is to stand up a single system that runs Instagram and WhatsApp conversations side-by-side without showing any seams to the user. Replies must read, sound, and time-out like a real person, while the logic underneath quietly segments each visitor, nurtures them, and pushes for the sale. Everything has to run on free or zero-cost APIs so I never pay per message. Think of an orchestration layer where multi-agent AI can plan, act, and learn: no-code flows in Zapier or n8n, autonomous GPT-style assistants for copy and decision making, and AIOps that spot bottlenecks and self-correct. If you need browser or desktop control, lean on open-source tools that can be hosted locally. Core acceptance criteria • Instagram: human-like DM replies, targeted engagement based on profile ...

I need an AI-powered voice agent that can make the phone, hold a truly natural conversation, and convert cold or warm leads into qualified prospects. Its core job is sales calls, and I want it to handle every stage — from initial lead generation through follow-ups and even short product demonstrations over the call. The experience for the prospect has to feel human: the bot should understand open-ended questions, respond contextually, and pivot when objections arise. I’m picturing a solution that dials out automatically, syncs with my CRM to pull and update lead data, and leaves detailed call notes when it’s done. If a call needs a live hand-off, it should transfer seamlessly to one of my reps. Key deliverables: • A deployable voice agent capable of outbound callin...

I’m preparing to launch an e-commerce website that will sell directly to consumers while doubling as a space where I share personal stories that reinforce the brand’s voice. The core build therefore needs to be an online store first, but with a seamless blog module baked in so I can publish narrative-driven posts without relying on separate platforms. Key components I need from you: • A modern storefront with secure checkout, inventory management, and product pages ready for rich media. • A robust user-account system so shoppers can register, track orders, save favorites, and receive tailored recommendations. • A lightweight blogging area styled consistently with the shop, optimized for readability and easy publishing of my personal stories. I’m op...